Application-Adaptive Performance Improvement in Mobile Systems by Using Persistent Memory

Bahn, Hyokyung The Institute of Internet 2019 Journal of Advanced Smart Convergence Vol.8 No.1

In this article, we present a performance enhancement scheme for mobile applications by adopting persistent memory. The proposed scheme supports the deadline guarantee of real-time applications like a video player, and also provides reasonable performances for non-real-time applications. To do so, we analyze the program execution path of mobile software platforms and find two sources of unpredictable time delays that make the deadline-guarantee of real-time applications difficult. The first is the irregular activation of garbage collection in flash storage and the second is the blocking and time-slice based scheduling used in mobile platforms. We resolve these two issues by adopting high performance persistent memory as the storage of real-time applications. By maintaining real-time applications and their data in persistent memory, I/O latency can become predictable because persistent memory does not need garbage collection. Also, we present a new scheduler that exclusively allocates a processor core to a real-time application. Although processor cycles can be wasted while a real-time application performs I/O, we depict that the processor utilization is not degraded significantly due to the acceleration of I/O by adopting persistent memory. Simulation experiments show that the proposed scheme improves the deadline misses of real-time applications by 90% in comparison with the legacy I/O scheme used in mobile systems.

Application-Adaptive Performance Improvement in Mobile Systems by Using Persistent Memory

Hyokyung Bahn 한국인터넷방송통신학회 2019 Journal of Advanced Smart Convergence Vol.8 No.1

In this article, we present a performance enhancement scheme for mobile applications by adopting persistent memory. The proposed scheme supports the deadline guarantee of real-time applications like a video player, and also provides reasonable performances for non-real-time applications. To do so, we analyze the program execution path of mobile software platforms and find two sources of unpredictable time delays that make the deadline-guarantee of real-time applications difficult. The first is the irregular activation of garbage collection in flash storage and the second is the blocking and time-slice based scheduling used in mobile platforms. We resolve these two issues by adopting high performance persistent memory as the storage of real-time applications. By maintaining real-time applications and their data in persistent memory, I/O latency can become predictable because persistent memory does not need garbage collection. Also, we present a new scheduler that exclusively allocates a processor core to a real-time application. Although processor cycles can be wasted while a real-time application performs I/O, we depict that the processor utilization is not degraded significantly due to the acceleration of I/O by adopting persistent memory. Simulation experiments show that the proposed scheme improves the deadline misses of real-time applications by 90% in comparison with the legacy I/O scheme used in mobile systems.

CPC: A File I/O Cache Management Policy for Compute-Bound Workloads

Bahn, Hyokyung The Institute of Internet 2022 International journal of advanced smart convergenc Vol.11 No.2

With the emergence of the new era of the 4th industrial revolution, compute-bound workloads with large memory footprint like big data processing increase dramatically. Even in such compute-bound workloads, however, we observe bulky I/Os while loading big data from storage to memory. Although file I/O cache plays a role of accelerating the performance of storage I/O, we found out that the cache hit rate in such environments is not improved even though we increase the file I/O cache capacity because of some special I/O references generated by compute-bound workloads. To cope with this situation, we propose a new file I/O cache management policy that improves the cache hit rate for compute-bound workloads significantly. Trace-driven simulations by replaying file I/O reference logs of compute-bound workloads show that the proposed cache management policy improves the cache hit rate compared to the well-acknowledged CLOCK algorithm by a large margin.

Characterization Studies on Data Access Bias in Mobile Platforms

Hyokyung Bahn 한국인터넷방송통신학회 2021 Journal of Advanced Smart Convergence Vol.10 No.4

Data access bias can be observed in various types of computing systems. In this paper, we characterize the data access bias in modern mobile computing platforms. In particular, we focus on the access bias of data observed at three different subsystems based on our experiences. First, we show the access bias of file data in mobile platforms. Second, we show the access bias of memory data in mobile platforms. Third, we show the access bias of web data and web servers. We expect that the characterization study in this paper will be helpful in the efficient management of mobile computing systems.

Analyzing Input Patterns of Smartphone Applications in Touch Interfaces

Hyokyung Bahn,Jisun Kim 한국인터넷방송통신학회 2021 Journal of Advanced Smart Convergence Vol.10 No.4

Touch sensor interface has become the most useful input device in a smartphone. Unlike keypad/keyboard interfaces used in electronic dictionaries and feature phones, smartphone’s touch interfaces allow for the recognition of various gestures that represent distinct features of each application’s input. In this paper, we analyze application-specific input patterns that appear in smartphone’s touch interfaces. Specifically, we capture touch input patterns from various Android applications, and analyze them. Based on this analysis, we observe a certain unique characteristics of application’s touch input patterns. This can be utilized in various useful areas like user authentications, prevention of executing application by illegal users, or digital forensic based on logged touch patterns.

Characterization Studies on Data Access Bias in Mobile Platforms

Bahn, Hyokyung The Institute of Internet 2021 International journal of advanced smart convergenc Vol.10 No.4

Data access bias can be observed in various types of computing systems. In this paper, we characterize the data access bias in modern mobile computing platforms. In particular, we focus on the access bias of data observed at three different subsystems based on our experiences. First, we show the access bias of file data in mobile platforms. Second, we show the access bias of memory data in mobile platforms. Third, we show the access bias of web data and web servers. We expect that the characterization study in this paper will be helpful in the efficient management of mobile computing systems.

Memory Allocation in Mobile Multitasking Environments with Real-time Constraints

Hyokyung Bahn 한국인터넷방송통신학회 2023 International Journal of Internet, Broadcasting an Vol.15 No.1

Due to the rapid performance improvement of smartphones, multitasking on mobile platforms has become an essential feature. Unlike traditional desktop or server environments, mobile applications are mostly interactive jobs where response time is important, and some applications are classified as real-time jobs with deadlines. When interactive and real-time jobs run concurrently, memory allocation between multitasking applications is a challenging issue as they have different time requirements. In this paper, we study how to allocate memory space when real-time and interactive jobs are simultaneously executed in a smartphone to meet the multitasking requirements between heterogeneous jobs. Specifically, we analyze the memory size required to satisfy the constraints of real-time jobs and present a new model for allocating memory space between heterogeneous multitasking jobs. Trace-driven simulations show that the proposed model provides reasonable performance for interactive jobs while guaranteeing the requirement of real-time jobs.

Analyzing Input Patterns of Smartphone Applications in Touch Interfaces

Bahn, Hyokyung,Kim, Jisun The Institute of Internet 2021 International journal of advanced smart convergenc Vol.10 No.4

Touch sensor interface has become the most useful input device in a smartphone. Unlike keypad/keyboard interfaces used in electronic dictionaries and feature phones, smartphone's touch interfaces allow for the recognition of various gestures that represent distinct features of each application's input. In this paper, we analyze application-specific input patterns that appear in smartphone's touch interfaces. Specifically, we capture touch input patterns from various Android applications, and analyze them. Based on this analysis, we observe a certain unique characteristics of application's touch input patterns. This can be utilized in various useful areas like user authentications, prevention of executing application by illegal users, or digital forensic based on logged touch patterns.

스마트 빌딩을 위한 센서 기반의 효율적인 엘리베이터 스케줄링

반효경(Hyokyung Bahn) 한국산학기술학회 2016 한국산학기술학회논문지 Vol.17 No.10

현대의 스마트 빌딩은 온도, 습도, 소리, 빛, 이동 등 다양한 물리적 정보를 감지해낼 수 있는 센서가 설치돼 있어 인간의 행동을 감지하고 추적하여 의료, 보안, 에너지 절약 등 각종 편의 시설에의 활용이 가능이다. 본 논문은 스마트 빌딩의 센서 기술을 이용하는 효율적인 엘리베이터 스케줄링 시스템을 제안한다. 스케줄링에 사용되는 센서로는 RFID, 비디오 센서, 바닥 센서 등으로 이들 센서는 엘리베이터 사용자의 도착 여부를 엘리베이터 호출 버튼을 누르기 전에 미리 감지하는 역할을 한다. 감지된 정보는 빌딩 네트워크를 통해 엘리베이터 스케줄링 시스템으로 전달되며, 제안하는 스케줄링 시스템은 이러한 정보를 통해 엘리베이터 사용자들을 위한 예약 호출을 생성하여 엘리베이터의 이동 방향과 이동 시간을 효율적으로 제어한다. 제안하는 엘리베이터 스케줄링 시스템의 성능을 평가하기 위해 다양한 워크로드 환경에서 모의 실험을 수행하였다. 그 결과 제안하는 스케줄링 시스템이 전통적인 엘리베이터 시스템보다 평균 대기 시간, 최악 대기 시간, 에너지 소모량 등에서 우수한 성능을 나타냄을 확인하였다. In a modern smart building, sensors can detect various physical conditions, such as temperature, humidity, sound, motion, and light, which can be used in medical services and security, and for energy savings. This paper presents an efficient elevator scheduling system that utilizes smart sensor technologies with radio-frequency identification, video, and floor sensors to detect the arrival of elevator users in advance. The detected information is then delivered to the elevator scheduling system via building networks. By using this information, the proposed system makes a reservation call for efficient control of the elevator"s direction and time. Experiments under a spectrum of traffic conditions show that the proposed system performs better than a legacy system with respect to average wait time, maximum wait time, and energy consumption.

유전 알고리즘을 이용한 웹 프락시 캐시의 교체 정책 설계

반효경(Hyokyung Bahn),조경운(Kyoungwoon Cho),고건(Kern Koh),문병로(Byungro Moon) 한국정보과학회 1999 정보과학회논문지 : 시스템 및 이론 Vol.26 No.6

WWW의 사용량이 대단히 빠르게 늘어남에 따라 웹 프락시 서버의 캐싱 기능은 그 중요성이 날로 증가하고 있다. 본 논문에서는 이러한 웹 프락시 캐시의 교체 정책을 웹 요구의 특성과 프락시 서버환경 자체를 고려하여 주어진 환경에 맞는 교체 정책이 되도록 유전 알고리즘을 사용하여 설계하는 방법을 제시하였다. 이 방법은 대부분의 기존 연구에서처럼 특정한 교체 정책 자체를 제시하는 것이 아니라, 주어진 프락시 환경에 적합한 교체 정책을 동적으로 설계할 수 있는 방법을 제시한다는 점에서 기존의 연구보다 일반성이 높다. As the demand for WWW increases rapidly, the importance of caching at proxy servers also increases day by day. In this paper, we design WWW proxy cache replacement policies which consider the characteristics of Web requests and the environment of proxy servers using genetic algorithms. Unlike most of previous works that show their fixed replacement policies, this approach provides a general framework for the design of appropriate replacement policies for dynamic proxy environments.